Huazhe Xu

29

Papers

209

Total Citations

Papers (29)

GenSim: Generating Robotic Simulation Tasks via Large Language Models

Diffusion Reward: Learning Rewards via Conditional Video Diffusion

Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control

4D Visual Pre-training for Robot Learning

Rethinking Transformers in Solving POMDPs

Natural Language Object Retrieval

End-To-End Learning of Driving Models From Large-Scale Video Datasets

Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes

Disentangling Propagation and Generation for Video Prediction

Hierarchical Style-based Networks for Motion Synthesis

Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation

ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL

Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss

Multi-Task Reinforcement Learning with Soft Modularization

Multi-Person 3D Motion Prediction with Multi-Range Transformers

NovelD: A Simple yet Effective Exploration Criterion

E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance

Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning

RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization

MoVie: Visual Model-Based Policy Adaptation for View Generalization

Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?

$\texttt{TACO}$: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning

H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation

CEIL: Generalized Contextual Imitation Learning